© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 10456
    Prev
    Next
    INDEX
    Explanations

    mentions of committee-related terms or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.75
    resp
    -0.72
    Pear
    -0.69
     Primal
    -0.66
     Ft
    -0.64
    stadt
    -0.63
    terior
    -0.62
     fasc
    -0.62
     Tide
    -0.61
     Fasc
    -0.61
    POSITIVE LOGITS
     committee
    1.17
     committees
    1.17
    ittee
    1.09
    ittees
    0.94
     chair
    0.93
     chairman
    0.92
    committee
    0.92
     chairs
    0.90
     subcommittee
    0.89
     hearings
    0.86
    Activations Density 0.019%

    No Known Activations